Aspect Extraction On Semeval 2014 Task 4 Sub 1
Metrics
Laptop (F1)
Mean F1 (Laptop + Restaurant)
Restaurant (F1)
Results
Performance results of various models on this benchmark
Model Name | Laptop (F1) | Mean F1 (Laptop + Restaurant) | Restaurant (F1) | Paper Title | Repository |
|---|---|---|---|---|---|
| PH-SUM | 86.09 | 84.215 | 82.34 | Improving BERT Performance for Aspect-Based Sentiment Analysis | |
| DE-CNN | - | - | 85.20 | Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction | |
| Wei et al. (2020) | 82.7 | - | 87.1 | Don't Eclipse Your Arts Due to Small Discrepancies: Boundary Repositioning with a Pointer Network for Aspect Extraction | - |
| ACE | 87.4 | - | 92.0 | Automated Concatenation of Embeddings for Structured Prediction | |
| InstructABSA | 92.30 | 92.53 | 92.76 | InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis | |
| BAT | 85.57 | 83.54 | 81.50 | Adversarial Training for Aspect-Based Sentiment Analysis with BERT |
0 of 6 row(s) selected.